Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5700 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.4503. Min Act: -0.1700
Data Index: 3307828 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.2003. Min Act: -0.1700
Data Index: 1726512 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.0753. Min Act: -0.1700
Data Index: 161391 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.1378. Min Act: -0.1700
Data Index: 1726510 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.1378. Min Act: -0.1700
Data Index: 4367490 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.0128. Min Act: -0.1700
Data Index: 5518212 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.9503. Min Act: -0.1700
Data Index: 3129468 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.0128. Min Act: -0.1700
Data Index: 3788662 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4503. Min Range: -10.4503
Max Act: 10.0128. Min Act: -0.1700
Data Index: 2895526 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.9503. Min Act: -0.1700
Data Index: 1367987 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8878. Min Act: -0.1700
Data Index: 4604283 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8253. Min Act: -0.1700
Data Index: 4249429 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8878. Min Act: -0.1700
Data Index: 318138 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8878. Min Act: -0.1700
Data Index: 4073020 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8878. Min Act: -0.1700
Data Index: 3031047 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8253. Min Act: -0.1700
Data Index: 1377384 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8878. Min Act: -0.1700
Data Index: 2755889 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.7628. Min Act: -0.1700
Data Index: 4519077 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8878. Min Act: -0.1700
Data Index: 3213321 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4503. Min Range: -10.4503
Max Act: 9.8253. Min Act: -0.1700
Data Index: 211871 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19